Best practices
Compression security
When implementing prompt compression, security and compliance are valid concerns. SuperCompress is designed with data privacy in mind.
Where does compression happen?
SuperCompress runs entirely on your infrastructure — CPU, no GPU needed, no external API calls. When you call compressor.compress(context, query), all processing happens in-process. No data leaves your machine unless you choose to use the hosted API.
Data residency
For teams with data residency requirements, self-host SuperCompress in your own cloud or on-premises environment. The MIT license allows unrestricted deployment.
Frequently asked questions
Does the local Compressor make any network calls?
No. The local Compressor is fully offline. No telemetry, no analytics, no external calls.
Is the compressed output auditable?
Yes. Log original and compressed text alongside the compression decision scores.
Build with less context
Put compression in front of your next LLM call.
Use the hosted API or run SuperCompress locally. Keep the evidence, drop the token waste, and measure the savings before it reaches your model.